About this integration
Exposes typed content-judgment questions through an optional local MCP server backed by TypeSafe's Jev service.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Package
- judgevet
- Last compatibility test
- Not independently tested
Connect your agent
judgevetThe publisher labels the documentation draft and the client unofficial. Calls send supplied content, questions and model selection to the configured service. Publisher documentation and the executable package manifest were reviewed; the package, MCP server and remote model service were not executed, and model quality, privacy or security was not independently audited.
Capabilities: Ask typed yes-probability, label-choice and rubric-score questions about supplied content, Return structured judgment values for caller-owned policy evaluation
Connected profiles
Additional details
judgevet
Source ↗ · Checked 2026-09-240.10.0
Source ↗ · Checked 2026-09-24The optional Python MCP entry point exposes three tools over a local stdio server.
Source ↗ · Checked 2026-09-24A TypeSafe API key must be supplied through the process environment or a secret provider for service calls.
Source ↗ · Checked 2026-09-24Install the optional MCP dependencies and configure the judgevet-mcp console entry point as the client's stdio command.
Source ↗ · Checked 2026-09-24Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-24